Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 22285
    Prev
    Next
    INDEX
    Explanations

    references to difficult situations or challenges that individuals or groups are facing

    oai_token-act-pair · gpt-3.5-turbo

    references to challenges or difficult situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ufact
    -0.81
    umin
    -0.68
    inet
    -0.68
     danced
    -0.67
    atche
    -0.66
    aware
    -0.65
    imore
    -0.64
    Aid
    -0.64
    neys
    -0.64
    ONSORED
    -0.63
    POSITIVE LOGITS
     dilemma
    1.18
     adversity
    1.07
     uphill
    1.05
     daunting
    1.04
     wrath
    0.98
     setback
    0.97
     predicament
    0.95
     dile
    0.93
     difficulties
    0.92
     temptation
    0.91
    Activations Density 0.129%

    No Known Activations